COMP 5420/4420: Natural Language Processing -- Spring 2026
Course description
In this course, we will study contemporary machine learning methods for understanding and generation of human language. If you have taken machine learning and know how to implement, train, and deploy a classifier -- and now you want to understand how to bridge the gap between that and contemporary language models that can answer questions and hold a conversation, this course is for you. Through a series of coding assignments, you will learn how to implement and train neural models to process language, from word-level embeddings to Transformer language models, including implementation, pre-training, fine-tuning and other modes of deployment of such models for handling different aspects of processing human language.
Pre-requisite: COMP 5420 / COMP 4420 Machine Learning or equivalent (with permission of instructor).
Course materials
Class recordings will be available on Echo.
Class-related discussions and announcements will be conducted on Discord.
Textbook
We may use materials from the following book, available online:
Daniel Jurafsky and James H. Martin.
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics,
and Speech Recognition with Language Models,
3rd edition (online manuscript).
Available at
https://web.stanford.edu/~jurafsky/slp3/
.
Staff
| Name | Contact | Office | Office hours | |
|---|---|---|---|---|
| Instructor | Anna Rumshisky | arumshisky@gmail.com | Dandeneau 318 | TBA |
| TA | Namrata Shivagunde | namrata_shivagunde@student.uml.edu | Dandeneau 415 | TBA |
| TA | Vijeta Deshpande | vijeta_deshpande@student.uml.edu | Dandeneau 415 | TBA |
| TA | Sherin Muckatira | sherinbojappa_muckatira@student.uml.edu | Dandeneau 415 | TBA |
Weekly Quizzes
This course uses a “prepare-then-quiz” structure rather than traditional graded homework submissions. Most weeks, we will assign a homework assignment following the lecture, which will be described at the end of class. You are explicitly permitted to use AI tools when completing these assignments, with the expectation that the homework is used for practice, exploration, and understanding rather than for submission. The homework itself will not be collected.
Instead, each week at the beginning of the next class, there will be an in-class closed book quiz covering (1) the conceptual material from the previous lecture and (2) the practical coding components introduced in the homework. Quizzes may ask you to reproduce parts of a homework solution and explain your reasoning. We will go over the quiz answers immediately after the quiz, before the lecture.
Please bring your laptop to class in order to follow the homework discussion and participate in occasional brief tutorials when assignments are introduced.
Homeworks
- Homeworks will be posted on the course website and linked from the course schedule.
- You do not need to submit your solutions.
Exams
Exams will be closed book and will assess your understanding of the theoretical concepts discussed in class as well as your ability to reason about and explain material covered in the homework assignments.
Research Paper Presentations
- Each student will be required to present a research paper assigned as readings for the class.
Grading
| Homeworks | No need to submit |
| In-Class Quizzes | 25% |
| Midterm Exam | 25% |
| Final Exam | 35% |
| Research Paper Presentations | 10% |
| Attendance and Participation | 5% |